Method and system for long-form answer extraction based on combination of sentence index generation techniques

US12111856B2 · kind B2 · utility

Assignee

• Tata Consultancy Services Limited · IN

Inventors

• Anumita Dasguptabandyopadhyay · Sherghati, IN
• PRABIR MALLICK · Sherghati, IN
• Tapas Nayak · Redmond, US
• Indrajit Bhattacharya · Melton, AU
• Sangameshwar Suryakant Patil · Jamkhed, IN

Key dates

• Filing date: Sep 20, 2023
• Grant date: Oct 8, 2024
• Expiry date: Sep 20, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06F16/3329
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

This disclosure relates generally to long-form answer extraction and, more particularly, to long-form answer extraction based on combination of sentence index generation techniques. Existing answer extractions techniques have achieved significant progress for extractive short answers; however, less progress has been made for long form questions that require explanations. Further the state-of-art long-answer extractions techniques result in poorer long-form answers or not address sparsity which becomes an issue longer contexts. Additionally, pre-trained generative sequence-to-sequence models are gaining popularity for factoid answer extraction tasks. Hence the disclosure proposes a long-form answer extraction based on several steps including training a set of generative sequence-to-sequence models comprising a sentence indices generation model and a sentence index spans generation. The trained set of generative sequence-to-sequence models is further utilized for model long-form answer extraction based on a union of several sentence index generation techniques comprising a sentence indices and a sentence index spans.